First Impression of DJI Pocket 3
Hands-on review of DJI Pocket 3 praising its portability and instant operation, but finding the video quality disappointing compared to iPhone 15 ProRes due to aggressive compression.
EN · 中
Computing Life · An engineering notebook
An engineering notebook on AI, systems, and everyday experiments.
Long-form notes on agentic systems, engineering judgment, astrophotography, hardware, coffee, and the tools that make a life easier to inspect and improve.
Latest
383 posts · since 2012
-
161
-
162
华山派剑宗气宗实力错位现象：一个多维度的学术探析
展示Claude V3.5长上下文和不偷懒特性的创意实验，以"剑宗的师叔气功好，气宗的徒儿剑法高"为题，让AI撰写了一篇13000字的学术论文，探讨金庸武侠中华山派的能力发展机制。
-
163
5分钟给全天相机加上云量识别功能
5分钟用AI给全天相机加上云量识别功能：利用GPT-4V理解云量，让AI自动编写调用API的代码，展示AI时代开发效率的革命性提升。
-
164
关于AI知识引擎的随想
构想一个AI知识引擎：自动收集会议和日常对话、提取有价值的知识并索引、在输出时及时提醒。三大挑战是数据采集、知识提取和实时参与。
-
165
Reflections on AI Knowledge Engines
Envisioning an AI knowledge engine that records conversations, extracts insights, and surfaces relevant knowledge when needed. Three key challenges: data collection, knowledge extraction, and real-time participation.
-
166
使用AI速读视频的技术收获
分享开发视频语音识别工具的技术心得：YouTube下载OAuth认证、异步任务API设计、Python并发挑战、GPT偷懒问题和iOS Shortcut集成。
-
167
Technical Insights on Using AI for Speed Reading Videos
Technical lessons from building an AI video transcription tool: YouTube OAuth2 authentication, async task-based APIs, Python concurrency patterns, GPT laziness issues, and iOS Shortcuts integration.
-
168
从微信群菜鸡互啄和AI代替人类工作看我们思考时到底应该追求什么
反思为何正确性不是思考的核心目标，提出真正重要的是纲举目张（Prioritization）、举一反三（Connection）和知行合一（Verification）三种能力。
-
169
视频信息密度那么低，为什么大家都在拍视频？
视频信息密度低、不可检索、难以跳转，但up主赚大钱而写文章不赚钱。核心在于视频让"作者"站到前台，观众更容易产生情感连接和付费意愿。
EN · 中 -
170
Why Do People Keep Making Videos When They're So Low in Information Density?
Videos are terrible for learning—can't skim, search, or navigate easily. Yet creators make millions because video makes the "author" tangible, lowering the barrier to payment. Articles hide the author behind ideas.
EN · 中